Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.8367. Min Act: -0.0000

Data Index: 627541 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7784. Min Act: -0.0000

Data Index: 329721 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1238159 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1784789 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7517. Min Act: -0.0000

Data Index: 856934 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1590816 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1481971 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1053309 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6994. Min Act: -0.0000

Data Index: 589485 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6753. Min Act: -0.0000

Data Index: 146029 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1747471 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6642. Min Act: -0.0000

Data Index: 191927 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7052. Min Act: -0.0000

Data Index: 372052 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1567553 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1387076 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1513171 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1308203 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1466370 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6012. Min Act: -0.0000

Data Index: 712294 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1327760 (The Pile)

Max Activating Token Index: 76